Writing archive · Page 5 of 9
More tutorials.
Same standard.
More entries from a 110-piece collection of tested, source-checked engineering notes.
- Evidence
- Working code, observable results, and primary sources.
- Judgment
- Tradeoffs, failure modes, and when not to use the technique.
- Freshness
- Every tutorial shows when it was reviewed—and a tested date only when its example was run.
Page 5 of 9
More from the archive.
Showing 49–60 of 107 archive entries.
- Read the tutorial
AI agents · Event sourcing · Reliability
Event-Sourced AI Agents: Replay, Debug, and Resume Any Run
Store immutable agent events, build deterministic projections, preserve model and tool outcomes, and recover safely after failures.
- Read the tutorial
Playwright · Coding agents · Testing
Generate and Heal Playwright Tests with Agents—Without Hiding Bugs
Use planner, generator, and healer agents under explicit evidence, security, and review gates so test maintenance does not weaken assertions.
- Read the tutorial
GraphRAG · Retrieval-augmented generation · Evaluation
GraphRAG vs Vector RAG: A Reproducible Benchmark Protocol
Compare graph and vector retrieval on local facts, multi-hop relationships, corpus-wide themes, latency, cost, freshness, and citation support.
- Read the tutorial
Computer-use agents · Accessibility · Browser automation
Ground Computer-Use Agents with Screenshots and Accessibility Trees
Fuse pixels with roles, names, states, geometry, and postcondition checks while detecting disagreement between visual and semantic UI representations.
- Read the tutorial
LLM routing · AI evaluation · Benchmarking
How to Benchmark a Multi-Model Router
A reproducible protocol for measuring a model router's quality, cost, latency, abstention, and resilience without cherry-picking.
- Read the tutorial
AI agent evaluation · Regression testing · Git bisect
How to Bisect an AI Agent Regression
Find the prompt, model, tool, data, or code change that caused an agent regression despite stochastic outcomes and external drift.
- Read the tutorial
AI agent evaluation · Evaluation datasets · AI testing
How to Build a High-Quality Agent Evaluation Dataset
Turn real agent tasks and failures into a versioned, reviewable evaluation dataset with defensible labels, provenance, and release coverage.
- Read the tutorial
AI agents · Performance · SRE
How to Build a Latency Budget for an AI Agent
Turn an end-to-end response target into measurable queue, model, tool, orchestration, and streaming budgets.
- Read the tutorial
AI agents · Incident response · Production reliability
How to Debug a Production AI Agent Incident
A containment-first incident playbook for agent models, tools, prompts, memory, retries, and ambiguous side effects.
- Read the tutorial
AI agents · SRE · AI evaluation
How to Define SLOs for AI Agents
Define measurable reliability, latency, quality, safety, and cost objectives around user outcomes—not model uptime.
- Read the tutorial
Voice agents · Evaluation · Speech interfaces
How to Evaluate a Voice Agent: Recognition, Turn Taking, Audio, and Task Success
Build a voice-agent evaluation suite that measures task outcomes, transcript errors, turn behavior, interruptions, audio delivery, safety, and user control.
- Read the tutorial
AI agents · Load testing · Reliability
How to Load Test Tool-Using AI Agents Safely
A reproducible load-testing protocol for agent queues, models, tools, retries, side effects, quality, and recovery.